Skip to main content
Glama

Prompt guard

prompt_guard
Read-onlyIdempotent

Prompt injection. Scan untrusted text for prompt injection, jailbreak attempts, delimiter spoofing, wallet exfiltration, and encoded payloads ($0.001). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without payment for the terms, sign them with your own wallet, call again with payment.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "prompt_guard"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesUntrusted text or prompt payload to scan (up to 32000 chars)
paymentNoa signed x402 payment (the base64 payload you would put in PAYMENT-SIGNATURE). Pass it and the purchase completes inside this tool call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered by structured data. The description's genuinely additive behavior is commercial: cost ($0.001 per call), accepted assets (USDC on Arc/Base/Solana, XNT on X1), and the two-step signed-payment requirement. It omits what a scan returns (verdict, risk score, flags), leaving the outcome format undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then cost, then payment mechanics in three compact sentences with no filler. The only minor redundancy is the repeated $0.001 figure, which is tolerable as a restatement of price in context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with no output schema, the description covers cost, assets, and the exact purchase sequence an agent must follow, which is the hardest part to infer. The remaining gap is the response shape (does it return a boolean, a risk score, matched categories?), which an agent would want before acting on results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are documented, giving a baseline of 3. The description goes beyond the schema by explaining that `payment` is not a one-shot argument: the first call yields terms that must be signed, and the signed payload is passed on a subsequent call. That workflow meaning is not visible in the schema text alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening states a specific verb+resource ("Scan untrusted text") and enumerates concrete detection classes (prompt injection, jailbreak, delimiter spoofing, wallet exfiltration, encoded payloads) that clearly separate it from generic siblings like agent_firewall. An agent knows exactly what this tool does before opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The payment flow is spelled out as a procedure: call once without `payment` to get terms, sign with your own wallet, call again with `payment`. That is clear operational context, but there is no guidance on when to prefer this over related scanners or when scanning is unnecessary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources